Skip to content
master
Go to file
Code

Latest commit

 

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
bin
 
 
 
 
 
 
kxy
 
 
 
 
 
 
 
 
 
 
 
 
 
 

README.md



KXY: A Powerful Serverless Analysis Toolkit That Takes Trial And Error Out of Machine Learning Projects

License PyPI Latest Release Downloads

Documentation

https://www.kxy.ai/reference/

Installation

From PyPi:

pip install kxy

From GitHub:

git clone https://github.com/kxytechnologies/kxy-python.git & cd ./kxy-python & pip install .

Authentication

All heavy-duty computations are run on our serverless infrastructure and require an API key. To configure the package with your API key, run

kxy configure

and follow the instructions. To request a demo and get a trial API key, contact us.

Docker

The Docker image kxytechnologies/kxy has been built for your convenience, and comes with anaconda, auto-sklearn, and the kxy package.

To start a Jupyter Notebook server from a sandboxed Docker environment, run

docker run -i -t -p 5555:8888 kxytechnologies/kxy:latest /bin/bash -c "kxy configure <YOUR API KEY> && /opt/conda/bin/jupyter notebook --notebook-dir=/opt/notebooks --ip='*' --port=8888 --no-browser --allow-root --NotebookApp.token=''"

where you should replace <YOUR API KEY> with your API key and navigate to http://localhost:5555 in your browser. This docker environment comes with all examples available on the documentation website.

To start a Jupyter Notebook server from an existing directory of notebooks, run

docker run -i -t --mount src=</path/to/your/local/dir>,target=/opt/notebooks,type=bind -p 5555:8888 kxytechnologies/kxy:latest /bin/bash -c "kxy configure <YOUR API KEY> && /opt/conda/bin/jupyter notebook --notebook-dir=/opt/notebooks --ip='*' --port=8888 --no-browser --allow-root --NotebookApp.token=''"

where you should replace </path/to/your/local/dir> with the path to your local notebook folder and navigate to http://localhost:5555 in your browser.

Applications

Higher ROI Machine Learning Projects

The kxy package utilizes information theory to takes trial and error out of machine learning projects.

From the get-go, the achievable performance analysis of the kxy package tells data scientists whether their datasets are sufficiently informative to achieve a performance (e.g. , maximum log-likelihood, and classification error) to their liking in a classification or regression problem, and if so what is the best performance that can be achieved using said datasets. No need to train tens of models to know what performance can be achieved.

The model-free variable selection analysis provided by the kxy package allows data scientists to train smaller models, faster, cheaper, and to achieve a higher performance than throwing all inputs in a big model or proceeding by trial-and-error.

Once a model has been trained, the kxy improvability analysis quantifies the extent to which the trained model can be improved without resorting to additional features. This allows data scientists to focus their modeling efforts on high ROI initiatives. No need to implement tens of fancy models on specialized hardware to see whether a trained model can be improved.

When a classification or regression model has successfully extracted all the value in using the features to predict the label, the kxy dataset valuation analysis allows data scientists to quickly quantify the performance increase (e.g. , maximum log-likelihood, and classification error) that a new dataset may bring about. No need to train or retrain tens of models with the new datasets to see whether the production model can be improved.

Model Audit

From understanding the marginal contribution of each variable towards the decision made by a black-box regression or classification model, to detecting bias in your trained classification and regression model, the kxy toolkit allows data scientists and decision markers to fully audit complex machine learning models.

Modern Financial Machine Learning

From non-Gaussian and memory-robust risk analysis, to alternative datasets valuation the kxy toolkit propels quants from the age of Gaussian distributions/linear regression/LASSO/Ridge/Random Forest into the age of modern machine learning, rigorously and cost-effectively.

About

A Powerful Serverless Analysis Toolkit That Takes Trial And Error Out of Machine Learning Projects

Topics

Resources

License

Languages

You can’t perform that action at this time.